{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 5GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\n%matplotlib inline\nimport seaborn as sns\nimport os","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.utils import to_categorical\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense, Dropout, Input\nfrom tensorflow.keras.layers import Activation, Flatten\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, ZeroPadding2D\nfrom tensorflow.keras.optimizers import SGD\nfrom tensorflow.keras.layers import BatchNormalization","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data=pd.read_csv('../input/Kannada-MNIST/train.csv')\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train= data.values[:6000, 1:]\ny_train=data.values[:6000, 0]\nn_classes=10\ny_train = to_categorical(y_train, n_classes) \n\n\nfrom sklearn.model_selection import train_test_split\nX_train, X_test, y_train, y_test = train_test_split(X_train, y_train, test_size=0.2, random_state=42)\n\nX_train = X_train.reshape((X_train.shape[0], 28, 28, 1))\nX_test = X_test.reshape((X_test.shape[0], 28, 28, 1))\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Data Augmentation, 课上需要教一下怎么使用"},{"metadata":{"trusted":true},"cell_type":"code","source":"from tensorflow.keras.preprocessing.image import ImageDataGenerator # for data augmentation\n\ndatagen = ImageDataGenerator(zoom_range=0.1,\n                             width_shift_range=0.3,\n                             height_shift_range=0.3,\n                             rotation_range=50)\ndatagen.fit(X_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_generator=datagen.flow(X_train, y_train, batch_size=32, shuffle=True)\nval_generator=datagen.flow(X_test,y_test, batch_size=64, shuffle=True)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Creat AlexNet, 如何调参？kernel size 如何决定，input shape不同的话如何影响？按照课上计算CNN每一层有多少参数吗？"},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\n\nmodel.add(Conv2D(32, kernel_size=(11,11), activation='relu', padding='same', input_shape=(28, 28, 1)))\n\nmodel.add(MaxPooling2D(3,3))\nmodel.add(BatchNormalization())\n\nmodel.add(Conv2D(32, kernel_size=(5,5), activation='relu', padding='same'))\nmodel.add(MaxPooling2D(3,3))\n\nmodel.add(Conv2D(128, kernel_size=(3,3), activation='relu', padding='same'))\nmodel.add(Conv2D(128, kernel_size=(3,3), activation='relu', padding='same'))\nmodel.add(Conv2D(128, kernel_size=(3,3), activation='relu', padding='same'))\nmodel.add(MaxPooling2D(3,3))\n\nmodel.add(Flatten())\nmodel.add(Dense(4096, activation='relu'))\nmodel.add(Dropout(0.25))\nmodel.add(Dense(4096, activation='relu'))\nmodel.add(Dropout(0.25))\n\nmodel.add(Dense(10, activation='softmax'))","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"model.compile(loss='categorical_crossentropy', optimizer='SGD', metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"AlexNet=model.fit(x=X_train, y=y_train,epochs=30,batch_size=128, validation_data=(X_test,y_test), shuffle=True)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"loss = AlexNet.history['loss']\nval_loss = AlexNet.history['val_loss']\n\nlen(loss)\n\ntrain_epoch=range(1,31)\nplt.plot(train_epoch,loss, label='loss')\nplt.plot(train_epoch,val_loss, label='validation_loss')\n\nplt.xlabel('Epoch')\nplt.ylabel('Loss')\nplt.legend()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"accuracy  = AlexNet.history['accuracy']\nval_accuracy = AlexNet.history['val_accuracy']\n\n\n\ntrain_epoch=range(1,31)\nplt.plot(train_epoch,accuracy , label='accuracy')\nplt.plot(train_epoch,val_accuracy , label='val_accuracy')\n\nplt.xlabel('Epoch')\nplt.ylabel('accuracy')\nplt.legend()\n\ntext=('best accuracy' ,max(val_accuracy),)\n\nplt.text(1,0.9940,text,fontsize =12)\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# alexNET with data Augmentation. 数据增强之后怎么提高不大啊？我用错了吗"},{"metadata":{"trusted":true},"cell_type":"code","source":"# Data augmentation\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator # for data augmentation\n\ndatagen = ImageDataGenerator(zoom_range=0.1,\n                             width_shift_range=0.3,\n                             height_shift_range=0.3,\n                             rotation_range=50)\ndatagen.fit(X_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"alex_data_aug=model.fit_generator(train_generator, steps_per_epoch = 150,epochs=30,\n                         validation_data=val_generator, validation_steps=10,shuffle=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"loss = alex_data_aug.history['loss']\nval_loss = alex_data_aug.history['val_loss']\n\nlen(loss)\n\ntrain_epoch=range(1,31)\nplt.plot(train_epoch,loss, label='loss')\nplt.plot(train_epoch,val_loss, label='validation_loss')\n\nplt.xlabel('Epoch')\nplt.ylabel('Loss')\nplt.legend()\nplt.title('AlexNet Data Augmentation Loss')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"accuracy  = alex_data_aug.history['accuracy']\nval_accuracy = alex_data_aug.history['val_accuracy']\n\n\n\ntrain_epoch=range(1,31)\nplt.plot(train_epoch,accuracy , label='accuracy')\nplt.plot(train_epoch,val_accuracy , label='val_accuracy')\n\nplt.xlabel('Epoch')\nplt.ylabel('accuracy')\nplt.legend()\n\ntext=('best accuracy' ,max(val_accuracy),)\n\nplt.text(1,0.6,text,fontsize =12)\nplt.title('AlexNet Data Augmentation accuracy')\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# VGG16"},{"metadata":{"trusted":true},"cell_type":"code","source":"model2 = Sequential()\n\nmodel2.add(Conv2D(16, kernel_size=(3,3), activation='relu', padding='same', input_shape=(28, 28, 1)))\nmodel2.add(Conv2D(16, kernel_size=(3,3), activation='relu', padding='same'))\nmodel2.add(MaxPooling2D(2,2))\nmodel2.add(BatchNormalization())\n\n\nmodel2.add(Conv2D(16, kernel_size=(3,3), activation='relu', padding='same', input_shape=(28, 28, 1)))\nmodel2.add(Conv2D(16, kernel_size=(3,3), activation='relu', padding='same'))\nmodel2.add(MaxPooling2D(2,2))\nmodel2.add(BatchNormalization())\nmodel2.summary()\n\nmodel2.add(Conv2D(64, kernel_size=(3,3), activation='relu', padding='same'))\nmodel2.add(Conv2D(64, kernel_size=(3,3), activation='relu', padding='same'))\nmodel2.add(Conv2D(64, kernel_size=(3,3), activation='relu', padding='same'))\nmodel2.add(MaxPooling2D(2,2))\nmodel2.add(BatchNormalization())\n\nmodel2.add(Conv2D(64, kernel_size=(3,3), activation='relu', padding='same'))\nmodel2.add(Conv2D(64, kernel_size=(3,3), activation='relu', padding='same'))\nmodel2.add(Conv2D(64, kernel_size=(3,3), activation='relu', padding='same'))\nmodel2.add(MaxPooling2D(2,2))\nmodel2.add(BatchNormalization())\n\nmodel2.summary()\n \n    #Should duplicate 3 times, but only 2. max pooling make it negative dimensions. \n\n\n\n\n\n\n\nmodel2.add(Flatten())\nmodel2.add(Dense(4096, activation='relu'))\nmodel2.add(Dropout(0.25))\nmodel2.add(Dense(4096, activation='relu'))\nmodel2.add(Dropout(0.25))\n\nmodel2.add(Dense(10, activation='softmax'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model2.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])\nVGG=model2.fit(x=X_train, y=y_train,epochs=30,batch_size=128, validation_data=(X_test,y_test), shuffle=True)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"accuracy  = VGG.history['accuracy']\nval_accuracy = VGG.history['val_accuracy']\n\n\n\ntrain_epoch=range(1,31)\nplt.plot(train_epoch,accuracy , label='accuracy')\nplt.plot(train_epoch,val_accuracy , label='val_accuracy')\n\nplt.xlabel('Epoch')\nplt.ylabel('accuracy')\nplt.legend()\n\ntext=('VGG best accuracy' ,max(val_accuracy),)\n\nplt.text(1,0.9940,text,fontsize =12)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_data=pd.read_csv('../input/Kannada-MNIST/test.csv')\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_data.values[0:, 1:].reshape(test_data.shape[0],28,28,1)\ntest_result=model2.predict(test_data.values[0:, 1:].reshape(test_data.shape[0],28,28,1))\nprint(test_result.shape)\ntest_res=np.argmax(test_result, axis=1, out=None)\ntest_res.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_data.shape\n\nsub=pd.DataFrame()\nsub['id']=list(test_data.values[0:,0])\n\n\nsub['label']=test_res\nsub.to_csv(\"submission.csv\", index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}